summaryrefslogtreecommitdiff
path: root/doc/CNN_V2.md
diff options
context:
space:
mode:
Diffstat (limited to 'doc/CNN_V2.md')
-rw-r--r--doc/CNN_V2.md7
1 files changed, 5 insertions, 2 deletions
diff --git a/doc/CNN_V2.md b/doc/CNN_V2.md
index b3b6587..9407934 100644
--- a/doc/CNN_V2.md
+++ b/doc/CNN_V2.md
@@ -13,10 +13,13 @@ CNN v2 extends the original CNN post-processing effect with parametric static fe
- Multi-frequency position encoding (NeRF-style)
- Per-layer configurable kernel sizes (1×1, 3×3, 5×5)
- Variable channel counts per layer
-- Float16 weight storage (GPU-optimized)
+- Float16 weight storage (~3.2 KB for 3-layer model)
- Bias integrated as static feature dimension
+- Storage buffer architecture (dynamic layer count)
+- Binary weight format for runtime loading
-**Status:** Design complete, ready for implementation
+**Status:** ✅ Complete. Training pipeline functional, validation tools ready.
+**TODO:** 8-bit quantization with QAT for 2× size reduction (~1.6 KB)
---